arXiv cs.CL· Leiyue Chen, Meng Wei, Xuefeng Hu, Wei Liu·· 14 小时前AI 评分26
Intervention-Certified Amplification：为 σ 加权后训练设置有效性门控
Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training
AI 导读
研究提出 Intervention-Certified Amplification（ICA），用配对 rollout 的目标证据对 σ 加权 SFT/RL 混合训练中的 σ 做门控。
正文 · 原文
Abstract:Hybrid post-training often mixes supervised fine-tuning (SFT) and reinforcement learning (RL), using training-side signals to set each sample's balance. Such signals characterize the anchor data and policy, but not whether the emphasized behavior helps in the target task and evaluation setting. This mismatch can reactivate and amplify pretrained behavior even after its literal form is removed from supervision. We demonstrate this with DIAA (Dual-Implicit Adversarial Amplification), a per-sample $\sigma$-weighted SFT/RL hybrid. With all literal Python fences removed from its anchor, DIAA emits unexecuted Tool-Integrated Reasoning (TIR) on $29%$ of MATH-500 prompts, three times vanilla GRPO. Paired interventions show $10.6$ percentage points of accuracy recovery when TIR is suppressed and comparable contributions from SFT imitation and $\sigma$-amplification; a student trained on a $0%$-TIR teacher anchor emits it at $45.8%$. Intervention-Certified Amplification (ICA) gates $\sigma$ with paired-rollout target evidence. Frozen and online ICA reduce TIR to $13.8%$ and $11.2%$, halve residual drag, improve accuracy from $47.5%$ to $48.7%$ and $49.3%$, and transfer to held-out GSM8K without retuning.
| Comments: | 13 pages, 2 figures, 4 tables. Published in Findings of the Association for Computational Linguistics: EMNLP 2026; see this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.33882 [cs.LG] |
| (or arXiv:2610.33882v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33882 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Findings of the Association for Computational Linguistics: EMNLP 2026, pages 44510-44522, Budapest, Hungary. Association for Computational Linguistics, 2026 |
Submission history
From: Leiyue Chen [view email]
[v1]
Sat, 24 Oct 2026 19:49:59 UTC (47 KB)
来源：arXiv cs.CL · arxiv.org